GenAI Security Evaluation Engineer

OpenTrain AI, Inc.; United States; Remote; USD 28,000 - 103,000; Part time

Benefits offered by this job

Remote work

Contract, part-time

Job summary

OpenTrain AI, Inc. is seeking a part-time, 100% remote contractor to build and test vulnerable and patched GenAI applications, tracing data and action flows, and evaluating authorization, prompt injection, and tool abuse.

The role requires at least three years in application security, secure code review, or vulnerability research, with strong English technical communication. Expect 20+ hours per week and work across global timelines.

Qualifications

• At least three years in application or product security, secure code review, penetration testing, or vulnerability research.
• Experience documenting security findings with precise code references.
• Experience writing exploit and reproduction tests to validate patches.

Responsibilities

• Define authorization contexts for actors, trust boundaries, tenants, permitted data and actions, purposes and recipients.
• Document findings with exact code spans, traps, control status and remediation recommendations.
• Write exploit and reproduction tests to demonstrate vulnerable behavior and verify patches.
• Evaluate issues such as sensitive information disclosure, prompt injection, tool abuse, and authorization flaws that scanners may miss.

Skills

Application security

Penetration testing

Vulnerability research

Code review

OWASP Top 10

Education

SWE/CSE degree or equivalent

OSCP or similar certification

Tools

CodeQL

Semgrep

SARIF

OpenTelemetry

Docker

Git

Job description

Build and test vulnerable and patched generative AI applications, trace data and action flows, and evaluate authorization, prompt injection, and tool abuse. This worldwide contractor role requires 20+ hours per week and strong application security experience.

100% Remote

Contract, part-time

Engagement

Remote

Location

Posted

The work

You will create and evaluate security tasks for generative AI applications, including agents and retrieval-augmented generation systems. The work covers vulnerable and patched implementations, authorization design, code-level findings, and tests that show whether security fixes work.

You will source or build GenAI applications, create vulnerable versions and patched counterparts, and trace data and action flows across files, callbacks, registries, and background jobs. You will also use a live model to demonstrate relevant paths when practical.

• Define authorization contexts for actors, trust boundaries, tenants, permitted data and actions, purposes, recipients, and document-level access.
• Document findings with exact code spans, traps, control status, and remediation recommendations.
• Write exploit and reproduction tests that demonstrate vulnerable behavior and confirm that patches prevent it.
• Evaluate issues such as sensitive information disclosure, excessive agency, prompt injection, tool abuse, and logic or authorization flaws that scanners may miss.

What it pays and takes

This is a part-time contractor role open worldwide. The listing does not provide a pay rate.

• Time requirement: 20+ hours per week.
• Language: Clear technical English is required.
• Required experience: At least three years in application or product security, secure code review, penetration testing, or vulnerability research.
• Required knowledge: Data-flow reasoning, authentication, authorization, least privilege, tenant isolation, trust boundaries, and approval flows.
• Required technical background: Production coding experience and knowledge of the OWASP Top 10 for LLM Applications.
• Valuable experience: CWE mapping, exploit and reproduction tests, CodeQL or Semgrep, SARIF, LLM tool calling, agents, MCP, RAG, memory, tracing, LangChain, LlamaIndex, relevant SDKs, OpenTelemetry, Docker, and Git.
• Helpful background: SWE, OSCP, GWAPT, or CSSLP credentials; CVE credits; bug bounty work; published security research; AI red-teaming; or LLM evaluation experience.

About AI training work

AI training is the human work behind systems that learn from examples, reviews, tests, and feedback. Security evaluators help identify unsafe behavior and improve how generative AI systems handle data, tools, permissions, and user requests.

Requirements

Job details

Location

100% remote

Languages

Engagement

Contract, part-time

Generative AI & RLHF

Data type

Computer Code Programming

Evaluation Rating, Red Teaming, Computer Programming Coding

Review AI-generated guidance about veterans benefits, claims, advocacy, and support resources. Use your Veterans Service Officer expertise to assess accuracy, clarity, empathy, and regulatory alignment for $20 to $50 per hour.

Evaluate conversational AI assistants through natural, multi-turn scenarios, compare their responses, and provide clear ratings and feedback. This remote project runs November 15 to November 18, requires about 7.5 hours, and pays $40 to $75 per hour.

Create digital paintings, character designs, concept art, animations, and other visual assets in Krita for an AI training project. This remote contractor role pays $21 to $70 per hour and requires clear English communication.

Use real plant and pilot data to create research-level chemical engineering problems for AI training. This flexible contract role pays $50 per hour and requires practical plant experience, technical writing, and Python or similar skills.

Remote · United Arab Emirates, Antigua and Barbuda, Albania +92 more

Create research-level AI problems using your power systems and protection expertise. Analyze relay records, test data, meter data, and fault records in a flexible remote contractor role paying $50 per hour.

Remote · United Arab Emirates, Antigua and Barbuda, Albania +92 more